Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    GPT examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    直し
    0.43
    Reminder
    0.39
     pabc
    0.38
     乀
    0.38
    Loan
    0.38
     жі
    0.38
    τως
    0.37
    ప్ర
    0.37
    莠
    0.37
    TreeView
    0.36
    POSITIVE LOGITS
     Australians
    0.49
     Sydney
    0.46
    safe
    0.44
     mieszkań
    0.44
    0.43
     surfers
    0.43
     mieszkańców
    0.43
    旅客
    0.42
    ជន
    0.42
     beach
    0.42
    Act Density 0.002%

    No Known Activations